The .csv files contain the aggregated results across model iterations, results of the corrected dependent t-test against the benchmark model as well as model configurations. Result tables are explained in the codebook file

The present work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression. Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained Random Forest Algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. The best performances were reached by our models involving early treatment characteristics (recall: 0.75-0.76; AUC: 0.71-0.77). Models trained on baseline data only were not significantly better than our benchmark. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features.